예제 #1
0
    def test_empty(self):
        # product of empty factors
        X = [[], [0, 1], []]
        Y = [[], [], ['a', 'b', 'c']]
        for x, y in zip(X, Y):
            expected1 = np.array([], dtype=np.asarray(x).dtype)
            expected2 = np.array([], dtype=np.asarray(y).dtype)
            result1, result2 = cartesian_product([x, y])
            tm.assert_numpy_array_equal(result1, expected1)
            tm.assert_numpy_array_equal(result2, expected2)

        # empty product (empty input):
        result = cartesian_product([])
        expected = []
        tm.assert_equal(result, expected)
예제 #2
0
    def test_empty(self):
        # product of empty factors
        X = [[], [0, 1], []]
        Y = [[], [], ['a', 'b', 'c']]
        for x, y in zip(X, Y):
            expected1 = np.array([], dtype=np.asarray(x).dtype)
            expected2 = np.array([], dtype=np.asarray(y).dtype)
            result1, result2 = cartesian_product([x, y])
            tm.assert_numpy_array_equal(result1, expected1)
            tm.assert_numpy_array_equal(result2, expected2)

        # empty product (empty input):
        result = cartesian_product([])
        expected = []
        tm.assert_equal(result, expected)
예제 #3
0
 def test_simple(self):
     x, y = list('ABC'), [1, 22]
     result1, result2 = cartesian_product([x, y])
     expected1 = np.array(['A', 'A', 'B', 'B', 'C', 'C'])
     expected2 = np.array([1, 22, 1, 22, 1, 22])
     tm.assert_numpy_array_equal(result1, expected1)
     tm.assert_numpy_array_equal(result2, expected2)
예제 #4
0
 def test_datetimeindex(self):
     # regression test for GitHub issue #6439
     # make sure that the ordering on datetimeindex is consistent
     x = date_range('2000-01-01', periods=2)
     result = [Index(y).day for y in cartesian_product([x, x])]
     expected = [np.array([1, 1, 2, 2]), np.array([1, 2, 1, 2])]
     assert_equal(result, expected)
예제 #5
0
 def test_simple(self):
     x, y = list('ABC'), [1, 22]
     result1, result2 = cartesian_product([x, y])
     expected1 = np.array(['A', 'A', 'B', 'B', 'C', 'C'])
     expected2 = np.array([1, 22, 1, 22, 1, 22])
     tm.assert_numpy_array_equal(result1, expected1)
     tm.assert_numpy_array_equal(result2, expected2)
예제 #6
0
 def test_datetimeindex(self):
     # regression test for GitHub issue #6439
     # make sure that the ordering on datetimeindex is consistent
     x = date_range('2000-01-01', periods=2)
     result = [Index(y).day for y in cartesian_product([x, x])]
     expected = [np.array([1, 1, 2, 2]), np.array([1, 2, 1, 2])]
     assert_equal(result, expected)
예제 #7
0
    def _apply_1d(self, func, axis):

        axis_name = self._get_axis_name(axis)
        ax = self._get_axis(axis)
        ndim = self.ndim
        values = self.values

        # iter thru the axes
        slice_axis = self._get_axis(axis)
        slice_indexer = [0]*(ndim-1)
        indexer = np.zeros(ndim, 'O')
        indlist = list(range(ndim))
        indlist.remove(axis)
        indexer[axis] = slice(None, None)
        indexer.put(indlist, slice_indexer)
        planes = [ self._get_axis(axi) for axi in indlist ]
        shape = np.array(self.shape).take(indlist)

        # all the iteration points
        points = cartesian_product(planes)

        results = []
        for i in range(np.prod(shape)):

            # construct the object
            pts = tuple([ p[i] for p in points ])
            indexer.put(indlist, slice_indexer)

            obj = Series(values[tuple(indexer)],index=slice_axis,name=pts)
            result = func(obj)

            results.append(result)

            # increment the indexer
            slice_indexer[-1] += 1
            n = -1
            while (slice_indexer[n] >= shape[n]) and (n > (1-ndim)):
                slice_indexer[n-1] += 1
                slice_indexer[n] = 0
                n -= 1

        # empty object
        if not len(results):
            return self._constructor(**self._construct_axes_dict())

        # same ndim as current
        if isinstance(results[0],Series):
            arr = np.vstack([ r.values for r in results ])
            arr = arr.T.reshape(tuple([len(slice_axis)] + list(shape)))
            tranp = np.array([axis]+indlist).argsort()
            arr = arr.transpose(tuple(list(tranp)))
            return self._constructor(arr,**self._construct_axes_dict())

        # ndim-1 shape
        results = np.array(results).reshape(shape)
        if results.ndim == 2 and axis_name != self._info_axis_name:
            results = results.T
            planes = planes[::-1]
        return self._construct_return_type(results,planes)
예제 #8
0
파일: panel.py 프로젝트: amirneto/pandas
    def _apply_1d(self, func, axis):

        axis_name = self._get_axis_name(axis)
        ax = self._get_axis(axis)
        ndim = self.ndim
        values = self.values

        # iter thru the axes
        slice_axis = self._get_axis(axis)
        slice_indexer = [0]*(ndim-1)
        indexer = np.zeros(ndim, 'O')
        indlist = list(range(ndim))
        indlist.remove(axis)
        indexer[axis] = slice(None, None)
        indexer.put(indlist, slice_indexer)
        planes = [ self._get_axis(axi) for axi in indlist ]
        shape = np.array(self.shape).take(indlist)

        # all the iteration points
        points = cartesian_product(planes)

        results = []
        for i in range(np.prod(shape)):

            # construct the object
            pts = tuple([ p[i] for p in points ])
            indexer.put(indlist, slice_indexer)

            obj = Series(values[tuple(indexer)],index=slice_axis,name=pts)
            result = func(obj)

            results.append(result)

            # increment the indexer
            slice_indexer[-1] += 1
            n = -1
            while (slice_indexer[n] >= shape[n]) and (n > (1-ndim)):
                slice_indexer[n-1] += 1
                slice_indexer[n] = 0
                n -= 1

        # empty object
        if not len(results):
            return self._constructor(**self._construct_axes_dict())

        # same ndim as current
        if isinstance(results[0],Series):
            arr = np.vstack([ r.values for r in results ])
            arr = arr.T.reshape(tuple([len(slice_axis)] + list(shape)))
            tranp = np.array([axis]+indlist).argsort()
            arr = arr.transpose(tuple(list(tranp)))
            return self._constructor(arr,**self._construct_axes_dict())

        # ndim-1 shape
        results = np.array(results).reshape(shape)
        if results.ndim == 2 and axis_name != self._info_axis_name:
            results = results.T
            planes = planes[::-1]
        return self._construct_return_type(results,planes)
예제 #9
0
 def test_simple(self):
     x, y = list('ABC'), [1, 22]
     result = cartesian_product([x, y])
     expected = [
         np.array(['A', 'A', 'B', 'B', 'C', 'C']),
         np.array([1, 22, 1, 22, 1, 22])
     ]
     assert_equal(result, expected)
예제 #10
0
 def test_datetimeindex(self):
     # regression test for GitHub issue #6439
     # make sure that the ordering on datetimeindex is consistent
     x = date_range('2000-01-01', periods=2)
     result1, result2 = [Index(y).day for y in cartesian_product([x, x])]
     expected1 = np.array([1, 1, 2, 2], dtype=np.int32)
     expected2 = np.array([1, 2, 1, 2], dtype=np.int32)
     tm.assert_numpy_array_equal(result1, expected1)
     tm.assert_numpy_array_equal(result2, expected2)
예제 #11
0
 def test_datetimeindex(self):
     # regression test for GitHub issue #6439
     # make sure that the ordering on datetimeindex is consistent
     x = date_range('2000-01-01', periods=2)
     result1, result2 = [Index(y).day for y in cartesian_product([x, x])]
     expected1 = np.array([1, 1, 2, 2], dtype=np.int32)
     expected2 = np.array([1, 2, 1, 2], dtype=np.int32)
     tm.assert_numpy_array_equal(result1, expected1)
     tm.assert_numpy_array_equal(result2, expected2)
예제 #12
0
    def setUp(self):
        tm._skip_if_no_scipy()
        import scipy.sparse
        # SparseSeries inputs used in tests, the tests rely on the order
        self.sparse_series = []
        s = pd.Series([3.0, nan, 1.0, 2.0, nan, nan])
        s.index = pd.MultiIndex.from_tuples([(1, 2, 'a', 0), (1, 2, 'a', 1),
                                             (1, 1, 'b', 0), (1, 1, 'b', 1),
                                             (2, 1, 'b', 0), (2, 1, 'b', 1)],
                                            names=['A', 'B', 'C', 'D'])
        self.sparse_series.append(s.to_sparse())

        ss = self.sparse_series[0].copy()
        ss.index.names = [3, 0, 1, 2]
        self.sparse_series.append(ss)

        ss = pd.Series([nan] * 12,
                       index=cartesian_product(
                           (range(3), range(4)))).to_sparse()
        for k, v in zip([(0, 0), (1, 2), (1, 3)], [3.0, 1.0, 2.0]):
            ss[k] = v
        self.sparse_series.append(ss)

        # results used in tests
        self.coo_matrices = []
        self.coo_matrices.append(
            scipy.sparse.coo_matrix(([3.0, 1.0, 2.0], ([0, 1, 1], [0, 2, 3])),
                                    shape=(3, 4)))
        self.coo_matrices.append(
            scipy.sparse.coo_matrix(([3.0, 1.0, 2.0], ([1, 0, 0], [0, 2, 3])),
                                    shape=(3, 4)))
        self.coo_matrices.append(
            scipy.sparse.coo_matrix(([3.0, 1.0, 2.0], ([0, 1, 1], [0, 0, 1])),
                                    shape=(3, 2)))
        self.ils = [[(1, 2), (1, 1), (2, 1)], [(1, 1), (1, 2), (2, 1)],
                    [(1, 2, 'a'), (1, 1, 'b'), (2, 1, 'b')]]
        self.jls = [[('a', 0), ('a', 1), ('b', 0), ('b', 1)], [0, 1]]
예제 #13
0
파일: test_series.py 프로젝트: jcfr/pandas
    def setUp(self):
        tm._skip_if_no_scipy()
        import scipy.sparse
        # SparseSeries inputs used in tests, the tests rely on the order
        self.sparse_series = []
        s = pd.Series([3.0, nan, 1.0, 2.0, nan, nan])
        s.index = pd.MultiIndex.from_tuples([(1, 2, 'a', 0),
                                             (1, 2, 'a', 1),
                                             (1, 1, 'b', 0),
                                             (1, 1, 'b', 1),
                                             (2, 1, 'b', 0),
                                             (2, 1, 'b', 1)],
                                            names=['A', 'B', 'C', 'D'])
        self.sparse_series.append(s.to_sparse())

        ss = self.sparse_series[0].copy()
        ss.index.names = [3, 0, 1, 2]
        self.sparse_series.append(ss)

        ss = pd.Series([
            nan
        ] * 12, index=cartesian_product((range(3), range(4)))).to_sparse()
        for k, v in zip([(0, 0), (1, 2), (1, 3)], [3.0, 1.0, 2.0]):
            ss[k] = v
        self.sparse_series.append(ss)

        # results used in tests
        self.coo_matrices = []
        self.coo_matrices.append(scipy.sparse.coo_matrix(
            ([3.0, 1.0, 2.0], ([0, 1, 1], [0, 2, 3])), shape=(3, 4)))
        self.coo_matrices.append(scipy.sparse.coo_matrix(
            ([3.0, 1.0, 2.0], ([1, 0, 0], [0, 2, 3])), shape=(3, 4)))
        self.coo_matrices.append(scipy.sparse.coo_matrix(
            ([3.0, 1.0, 2.0], ([0, 1, 1], [0, 0, 1])), shape=(3, 2)))
        self.ils = [[(1, 2), (1, 1), (2, 1)], [(1, 1), (1, 2), (2, 1)],
                    [(1, 2, 'a'), (1, 1, 'b'), (2, 1, 'b')]]
        self.jls = [[('a', 0), ('a', 1), ('b', 0), ('b', 1)], [0, 1]]
예제 #14
0
def pivot_table(data,
                values=None,
                index=None,
                columns=None,
                aggfunc='mean',
                fill_value=None,
                margins=False,
                dropna=True):
    """
    Create a spreadsheet-style pivot table as a DataFrame. The levels in the
    pivot table will be stored in MultiIndex objects (hierarchical indexes) on
    the index and columns of the result DataFrame

    Parameters
    ----------
    data : DataFrame
    values : column to aggregate, optional
    index : a column, Grouper, array which has the same length as data, or list of them.
        Keys to group by on the pivot table index.
        If an array is passed, it is being used as the same manner as column values.
    columns : a column, Grouper, array which has the same length as data, or list of them.
        Keys to group by on the pivot table column.
        If an array is passed, it is being used as the same manner as column values.
    aggfunc : function, default numpy.mean, or list of functions
        If list of functions passed, the resulting pivot table will have
        hierarchical columns whose top level are the function names (inferred
        from the function objects themselves)
    fill_value : scalar, default None
        Value to replace missing values with
    margins : boolean, default False
        Add all row / columns (e.g. for subtotal / grand totals)
    dropna : boolean, default True
        Do not include columns whose entries are all NaN
    rows : kwarg only alias of index [deprecated]
    cols : kwarg only alias of columns [deprecated]

    Examples
    --------
    >>> df
       A   B   C      D
    0  foo one small  1
    1  foo one large  2
    2  foo one large  2
    3  foo two small  3
    4  foo two small  3
    5  bar one large  4
    6  bar one small  5
    7  bar two small  6
    8  bar two large  7

    >>> table = pivot_table(df, values='D', index=['A', 'B'],
    ...                     columns=['C'], aggfunc=np.sum)
    >>> table
              small  large
    foo  one  1      4
         two  6      NaN
    bar  one  5      4
         two  6      7

    Returns
    -------
    table : DataFrame
    """
    index = _convert_by(index)
    columns = _convert_by(columns)

    if isinstance(aggfunc, list):
        pieces = []
        keys = []
        for func in aggfunc:
            table = pivot_table(data,
                                values=values,
                                index=index,
                                columns=columns,
                                fill_value=fill_value,
                                aggfunc=func,
                                margins=margins)
            pieces.append(table)
            keys.append(func.__name__)
        return concat(pieces, keys=keys, axis=1)

    keys = index + columns

    values_passed = values is not None
    if values_passed:
        if isinstance(values, (list, tuple)):
            values_multi = True
        else:
            values_multi = False
            values = [values]
    else:
        values = list(data.columns.drop(keys))

    if values_passed:
        to_filter = []
        for x in keys + values:
            if isinstance(x, Grouper):
                x = x.key
            try:
                if x in data:
                    to_filter.append(x)
            except TypeError:
                pass
        if len(to_filter) < len(data.columns):
            data = data[to_filter]

    grouped = data.groupby(keys)
    agged = grouped.agg(aggfunc)

    table = agged
    if table.index.nlevels > 1:
        to_unstack = [
            agged.index.names[i] or i for i in range(len(index), len(keys))
        ]
        table = agged.unstack(to_unstack)

    if not dropna:
        try:
            m = MultiIndex.from_arrays(cartesian_product(table.index.levels))
            table = table.reindex_axis(m, axis=0)
        except AttributeError:
            pass  # it's a single level

        try:
            m = MultiIndex.from_arrays(cartesian_product(table.columns.levels))
            table = table.reindex_axis(m, axis=1)
        except AttributeError:
            pass  # it's a single level or a series

    if isinstance(table, DataFrame):
        if isinstance(table.columns, MultiIndex):
            table = table.sortlevel(axis=1)
        else:
            table = table.sort_index(axis=1)

    if fill_value is not None:
        table = table.fillna(value=fill_value, downcast='infer')

    if margins:
        table = _add_margins(table,
                             data,
                             values,
                             rows=index,
                             cols=columns,
                             aggfunc=aggfunc)

    # discard the top level
    if values_passed and not values_multi:
        table = table[values[0]]

    if len(index) == 0 and len(columns) > 0:
        table = table.T

    return table
예제 #15
0
파일: pivot.py 프로젝트: IcyLeez/pandas
def pivot_table(data, values=None, index=None, columns=None, aggfunc='mean',
                fill_value=None, margins=False, dropna=True, **kwarg):
    """
    Create a spreadsheet-style pivot table as a DataFrame. The levels in the
    pivot table will be stored in MultiIndex objects (hierarchical indexes) on
    the index and columns of the result DataFrame

    Parameters
    ----------
    data : DataFrame
    values : column to aggregate, optional
    index : list of column names or arrays to group on
        Keys to group on the x-axis of the pivot table
    columns : list of column names or arrays to group on
        Keys to group on the y-axis of the pivot table
    aggfunc : function, default numpy.mean, or list of functions
        If list of functions passed, the resulting pivot table will have
        hierarchical columns whose top level are the function names (inferred
        from the function objects themselves)
    fill_value : scalar, default None
        Value to replace missing values with
    margins : boolean, default False
        Add all row / columns (e.g. for subtotal / grand totals)
    dropna : boolean, default True
        Do not include columns whose entries are all NaN
    rows : kwarg only alias of index [deprecated]
    cols : kwarg only alias of columns [deprecated]

    Examples
    --------
    >>> df
       A   B   C      D
    0  foo one small  1
    1  foo one large  2
    2  foo one large  2
    3  foo two small  3
    4  foo two small  3
    5  bar one large  4
    6  bar one small  5
    7  bar two small  6
    8  bar two large  7

    >>> table = pivot_table(df, values='D', index=['A', 'B'],
    ...                     columns=['C'], aggfunc=np.sum)
    >>> table
              small  large
    foo  one  1      4
         two  6      NaN
    bar  one  5      4
         two  6      7

    Returns
    -------
    table : DataFrame
    """
    # Parse old-style keyword arguments
    rows = kwarg.pop('rows', None)
    if rows is not None:
        warnings.warn("rows is deprecated, use index", FutureWarning)
        if index is None:
            index = rows
        else:
            msg = "Can only specify either 'rows' or 'index'"
            raise TypeError(msg)

    cols = kwarg.pop('cols', None)
    if cols is not None:
        warnings.warn("cols is deprecated, use columns", FutureWarning)
        if columns is None:
            columns = cols
        else:
            msg = "Can only specify either 'cols' or 'columns'"
            raise TypeError(msg)
    
    if kwarg:
        raise TypeError("Unexpected argument(s): %s" % kwarg.keys())
    
    index = _convert_by(index)
    columns = _convert_by(columns)

    if isinstance(aggfunc, list):
        pieces = []
        keys = []
        for func in aggfunc:
            table = pivot_table(data, values=values, index=index, columns=columns,
                                fill_value=fill_value, aggfunc=func,
                                margins=margins)
            pieces.append(table)
            keys.append(func.__name__)
        return concat(pieces, keys=keys, axis=1)

    keys = index + columns

    values_passed = values is not None
    if values_passed:
        if isinstance(values, (list, tuple)):
            values_multi = True
        else:
            values_multi = False
            values = [values]
    else:
        values = list(data.columns.drop(keys))

    if values_passed:
        to_filter = []
        for x in keys + values:
            try:
                if x in data:
                    to_filter.append(x)
            except TypeError:
                pass
        if len(to_filter) < len(data.columns):
            data = data[to_filter]

    grouped = data.groupby(keys)
    agged = grouped.agg(aggfunc)

    table = agged
    if table.index.nlevels > 1:
        to_unstack = [agged.index.names[i]
                      for i in range(len(index), len(keys))]
        table = agged.unstack(to_unstack)

    if not dropna:
        try:
            m = MultiIndex.from_arrays(cartesian_product(table.index.levels))
            table = table.reindex_axis(m, axis=0)
        except AttributeError:
            pass # it's a single level

        try:
            m = MultiIndex.from_arrays(cartesian_product(table.columns.levels))
            table = table.reindex_axis(m, axis=1)
        except AttributeError:
            pass # it's a single level or a series

    if isinstance(table, DataFrame):
        if isinstance(table.columns, MultiIndex):
            table = table.sortlevel(axis=1)
        else:
            table = table.sort_index(axis=1)

    if fill_value is not None:
        table = table.fillna(value=fill_value, downcast='infer')

    if margins:
        table = _add_margins(table, data, values, rows=index,
                             cols=columns, aggfunc=aggfunc)

    # discard the top level
    if values_passed and not values_multi:
        table = table[values[0]]

    if len(index) == 0 and len(columns) > 0:
        table = table.T

    return table
예제 #16
0
파일: test_util.py 프로젝트: APWaldo/pandas
 def test_simple(self):
     x, y = list('ABC'), [1, 22]
     result = cartesian_product([x, y])
     expected = [np.array(['A', 'A', 'B', 'B', 'C', 'C']),
                 np.array([ 1, 22,  1, 22,  1, 22])]
     assert_equal(result, expected)
예제 #17
0
파일: pivot.py 프로젝트: cscanlin/pandas
def pivot_table(data, values=None, index=None, columns=None, aggfunc='mean',
                fill_value=None, margins=False, dropna=True,
                margins_name='All'):
    """
    Create a spreadsheet-style pivot table as a DataFrame. The levels in the
    pivot table will be stored in MultiIndex objects (hierarchical indexes) on
    the index and columns of the result DataFrame

    Parameters
    ----------
    data : DataFrame
    values : column to aggregate, optional
    index : column, Grouper, array, or list of the previous
        If an array is passed, it must be the same length as the data. The list
        can contain any of the other types (except list).
        Keys to group by on the pivot table index.  If an array is passed, it
        is being used as the same manner as column values.
    columns : column, Grouper, array, or list of the previous
        If an array is passed, it must be the same length as the data. The list
        can contain any of the other types (except list).
        Keys to group by on the pivot table column.  If an array is passed, it
        is being used as the same manner as column values.
    aggfunc : function or list of functions, default numpy.mean
        If list of functions passed, the resulting pivot table will have
        hierarchical columns whose top level are the function names (inferred
        from the function objects themselves)
    fill_value : scalar, default None
        Value to replace missing values with
    margins : boolean, default False
        Add all row / columns (e.g. for subtotal / grand totals)
    dropna : boolean, default True
        Do not include columns whose entries are all NaN
    margins_name : string, default 'All'
        Name of the row / column that will contain the totals
        when margins is True.

    Examples
    --------
    >>> df
       A   B   C      D
    0  foo one small  1
    1  foo one large  2
    2  foo one large  2
    3  foo two small  3
    4  foo two small  3
    5  bar one large  4
    6  bar one small  5
    7  bar two small  6
    8  bar two large  7

    >>> table = pivot_table(df, values='D', index=['A', 'B'],
    ...                     columns=['C'], aggfunc=np.sum)
    >>> table
              small  large
    foo  one  1      4
         two  6      NaN
    bar  one  5      4
         two  6      7

    Returns
    -------
    table : DataFrame
    """
    index = _convert_by(index)
    columns = _convert_by(columns)

    if isinstance(aggfunc, list):
        pieces = []
        keys = []
        for func in aggfunc:
            table = pivot_table(data, values=values, index=index,
                                columns=columns,
                                fill_value=fill_value, aggfunc=func,
                                margins=margins)
            pieces.append(table)
            keys.append(func.__name__)
        return concat(pieces, keys=keys, axis=1)

    keys = index + columns

    values_passed = values is not None
    if values_passed:
        if com.is_list_like(values):
            values_multi = True
            values = list(values)
        else:
            values_multi = False
            values = [values]
    else:
        values = list(data.columns.drop(keys))

    if values_passed:
        to_filter = []
        for x in keys + values:
            if isinstance(x, Grouper):
                x = x.key
            try:
                if x in data:
                    to_filter.append(x)
            except TypeError:
                pass
        if len(to_filter) < len(data.columns):
            data = data[to_filter]

    grouped = data.groupby(keys)
    agged = grouped.agg(aggfunc)

    table = agged
    if table.index.nlevels > 1:
        to_unstack = [agged.index.names[i] or i
                      for i in range(len(index), len(keys))]
        table = agged.unstack(to_unstack)

    if not dropna:
        try:
            m = MultiIndex.from_arrays(cartesian_product(table.index.levels))
            table = table.reindex_axis(m, axis=0)
        except AttributeError:
            pass  # it's a single level

        try:
            m = MultiIndex.from_arrays(cartesian_product(table.columns.levels))
            table = table.reindex_axis(m, axis=1)
        except AttributeError:
            pass  # it's a single level or a series

    if isinstance(table, DataFrame):
        if isinstance(table.columns, MultiIndex):
            table = table.sortlevel(axis=1)
        else:
            table = table.sort_index(axis=1)

    if fill_value is not None:
        table = table.fillna(value=fill_value, downcast='infer')

    if margins:
        table = _add_margins(table, data, values, rows=index,
                             cols=columns, aggfunc=aggfunc,
                             margins_name=margins_name)

    # discard the top level
    if values_passed and not values_multi:
        table = table[values[0]]

    if len(index) == 0 and len(columns) > 0:
        table = table.T

    return table
예제 #18
0
def pivot_table(data,
                values=None,
                index=None,
                columns=None,
                aggfunc='mean',
                fill_value=None,
                margins=False,
                dropna=True,
                margins_name='All'):
    """
    Create a spreadsheet-style pivot table as a DataFrame. The levels in the
    pivot table will be stored in MultiIndex objects (hierarchical indexes) on
    the index and columns of the result DataFrame

    Parameters
    ----------
    data : DataFrame
    values : column to aggregate, optional
    index : column, Grouper, array, or list of the previous
        If an array is passed, it must be the same length as the data. The list
        can contain any of the other types (except list).
        Keys to group by on the pivot table index.  If an array is passed, it
        is being used as the same manner as column values.
    columns : column, Grouper, array, or list of the previous
        If an array is passed, it must be the same length as the data. The list
        can contain any of the other types (except list).
        Keys to group by on the pivot table column.  If an array is passed, it
        is being used as the same manner as column values.
    aggfunc : function or list of functions, default numpy.mean
        If list of functions passed, the resulting pivot table will have
        hierarchical columns whose top level are the function names (inferred
        from the function objects themselves)
    fill_value : scalar, default None
        Value to replace missing values with
    margins : boolean, default False
        Add all row / columns (e.g. for subtotal / grand totals)
    dropna : boolean, default True
        Do not include columns whose entries are all NaN
    margins_name : string, default 'All'
        Name of the row / column that will contain the totals
        when margins is True.

    Examples
    --------
    >>> df
       A   B   C      D
    0  foo one small  1
    1  foo one large  2
    2  foo one large  2
    3  foo two small  3
    4  foo two small  3
    5  bar one large  4
    6  bar one small  5
    7  bar two small  6
    8  bar two large  7

    >>> table = pivot_table(df, values='D', index=['A', 'B'],
    ...                     columns=['C'], aggfunc=np.sum)
    >>> table
              small  large
    foo  one  1      4
         two  6      NaN
    bar  one  5      4
         two  6      7

    Returns
    -------
    table : DataFrame

    See also
    --------
    DataFrame.pivot : pivot without aggregation that can handle
        non-numeric data
    """
    index = _convert_by(index)
    columns = _convert_by(columns)

    if isinstance(aggfunc, list):
        pieces = []
        keys = []
        for func in aggfunc:
            table = pivot_table(data,
                                values=values,
                                index=index,
                                columns=columns,
                                fill_value=fill_value,
                                aggfunc=func,
                                margins=margins,
                                margins_name=margins_name)
            pieces.append(table)
            keys.append(func.__name__)
        return concat(pieces, keys=keys, axis=1)

    keys = index + columns

    values_passed = values is not None
    if values_passed:
        if is_list_like(values):
            values_multi = True
            values = list(values)
        else:
            values_multi = False
            values = [values]

        # GH14938 Make sure value labels are in data
        for i in values:
            if i not in data:
                raise KeyError(i)

        to_filter = []
        for x in keys + values:
            if isinstance(x, Grouper):
                x = x.key
            try:
                if x in data:
                    to_filter.append(x)
            except TypeError:
                pass
        if len(to_filter) < len(data.columns):
            data = data[to_filter]

    else:
        values = data.columns
        for key in keys:
            try:
                values = values.drop(key)
            except (TypeError, ValueError):
                pass
        values = list(values)

    grouped = data.groupby(keys)
    agged = grouped.agg(aggfunc)

    table = agged
    if table.index.nlevels > 1:
        to_unstack = [
            agged.index.names[i] or i for i in range(len(index), len(keys))
        ]
        table = agged.unstack(to_unstack)

    if not dropna:
        try:
            m = MultiIndex.from_arrays(cartesian_product(table.index.levels),
                                       names=table.index.names)
            table = table.reindex_axis(m, axis=0)
        except AttributeError:
            pass  # it's a single level

        try:
            m = MultiIndex.from_arrays(cartesian_product(table.columns.levels),
                                       names=table.columns.names)
            table = table.reindex_axis(m, axis=1)
        except AttributeError:
            pass  # it's a single level or a series

    if isinstance(table, DataFrame):
        if isinstance(table.columns, MultiIndex):
            table = table.sortlevel(axis=1)
        else:
            table = table.sort_index(axis=1)

    if fill_value is not None:
        table = table.fillna(value=fill_value, downcast='infer')

    if margins:
        if dropna:
            data = data[data.notnull().all(axis=1)]
        table = _add_margins(table,
                             data,
                             values,
                             rows=index,
                             cols=columns,
                             aggfunc=aggfunc,
                             margins_name=margins_name)

    # discard the top level
    if values_passed and not values_multi and not table.empty:
        table = table[values[0]]

    if len(index) == 0 and len(columns) > 0:
        table = table.T

    return table
예제 #19
0
 def test_simple(self):
     x, y = list("ABC"), [1, 22]
     result = cartesian_product([x, y])
     expected = [np.array(["A", "A", "B", "B", "C", "C"]), np.array([1, 22, 1, 22, 1, 22])]
     assert_equal(result, expected)